Spaces:
Running
Running
| import re | |
| import json | |
| import gradio as gr | |
| # Your model’s raw NER output (we trust these start/end indices) | |
| ner = [ | |
| { | |
| 'start': 11, | |
| 'end': 29, | |
| 'text': 'Home Visits Survey', | |
| 'label': 'named dataset', | |
| 'score': 0.9947463870048523 | |
| } | |
| ] | |
| # Your model’s raw RE output | |
| relations = { | |
| 'Home Visits Survey': [ | |
| {'source': 'Home Visits Survey', 'relation': 'data geography', 'target': 'Jordan', 'score': 0.6180844902992249}, | |
| {'source': 'Home Visits Survey', 'relation': 'version', 'target': 'Round II', 'score': 0.9688164591789246}, | |
| {'source': 'Home Visits Survey', 'relation': 'acronym', 'target': 'HV', 'score': 0.9140607714653015}, | |
| {'source': 'Home Visits Survey', 'relation': 'author', 'target': 'UNHCR', 'score': 0.7762154340744019}, | |
| {'source': 'Home Visits Survey', 'relation': 'author', 'target': 'World Food Programme', 'score': 0.6582539677619934}, | |
| {'source': 'Home Visits Survey', 'relation': 'reference year', 'target': '2013', 'score': 0.524115264415741}, | |
| {'source': 'Home Visits Survey', 'relation': 'publication year', 'target': '2014', 'score': 0.6853994131088257}, | |
| {'source': 'Home Visits Survey', 'relation': 'data description', 'target': 'detailed socio-economic, health, and protection data', 'score': 0.6544178128242493}, | |
| ] | |
| } | |
| # Exact sample text | |
| SAMPLE_TEXT = """The Jordan Home Visits Survey, Round II (HV), was carried out by UNHCR and the World Food Programme between November 2013 and September 2014. Through in-home visits to Syrian refugee households in Jordan, it gathered detailed socio-economic, health, and protection data—each household tagged with a unique ID to allow longitudinal tracking.""" | |
| def highlight_text(text): | |
| entities = [] | |
| # 1) NER spans | |
| for ent in ner: | |
| entities.append({ | |
| "entity": ent["label"], | |
| "start": ent["start"], | |
| "end": ent["end"], | |
| }) | |
| # 2) RE spans | |
| for rel_list in relations.values(): | |
| for r in rel_list: | |
| for m in re.finditer(re.escape(r["target"]), text): | |
| entities.append({ | |
| "entity": r["relation"], | |
| "start": m.start(), | |
| "end": m.end(), | |
| }) | |
| return {"text": text, "entities": entities} | |
| def get_model_predictions(): | |
| return json.dumps({"ner": ner, "relations": relations}, indent=2) | |
| with gr.Blocks() as demo: | |
| gr.Markdown("## Data Use Detector\n" | |
| "Edit the sample text, then click **Highlight** to annotate entities, or **Get Model Predictions** to see the raw JSON.") | |
| txt_in = gr.Textbox(label="Input Text", lines=4, value=SAMPLE_TEXT) | |
| highlight_btn = gr.Button("Highlight") | |
| txt_out = gr.HighlightedText(label="Annotated Entities") | |
| get_pred_btn = gr.Button("Get Model Predictions") | |
| ner_rel_box = gr.Textbox( | |
| label="Model Predictions (JSON)", | |
| lines=15, | |
| value="", | |
| interactive=False | |
| ) | |
| # Only trigger highlighting on click | |
| highlight_btn.click(fn=highlight_text, inputs=txt_in, outputs=txt_out) | |
| # Only show preds on click | |
| get_pred_btn.click(fn=get_model_predictions, inputs=None, outputs=ner_rel_box) | |
| if __name__ == "__main__": | |
| demo.launch() | |